klammertext/tst/cond_test.sh

#!/bin/bash
#
# cond_test.sh — Regression tests for @cond argument delimitation.
#
# These tests pin down the fix for the bug witnessed by tst/cond_test.kt:
# a defined klammer that contains its own bar separators (e.g. @frac a | b @)
# nested inside a @cond branch caused @cond to miscount bars and reject the
# input with "There should only be one or two bar characters".
#
# Root cause: @cond delimited its arguments by counting EVERY bar in its flat
# katom range, conflating the inner klammer's bars (which belong to the inner
# klammer's arity) with @cond's own separators.  The fix counts only the bars
# at nesting depth 0 within the @cond span (cond_separator_bars() in
# mac/machine.cpp), so argument boundaries follow the span tree.
#
# See doc/cond_evaluation_order.md for the full description and the
# theoretical basis (operadic arity, the precedence-order proposition, and
# @cond as a non-strict special form).
#
# Usage: ./cond_test.sh   (LSan suppressions come from env/runtime.env.*)
# Exit code: 0 if all tests pass, 1 otherwise.

PASS=0
FAIL=0
KTEXT=ktext
K=${KLAMMERTEXT_HOME:?KLAMMERTEXT_HOME must be set}

red=$'\033[31m'
green=$'\033[32m'
bold=$'\033[1m'
reset=$'\033[0m'

# strip leading/trailing blank lines and surrounding whitespace
trim() { awk '{ sub(/[ \t\r]+$/, "") } { line[NR]=$0 } END { f=1; while (f<=NR && line[f]=="") f++; l=NR; while (l>=1 && line[l]=="") l--; for (i=f;i<=l;i++) print line[i] }'; }

# check_eq TEST_NAME EXPECTED KTEXT_ARGS...
#   Runs ktext, expects exit status 0, and compares trimmed stdout to EXPECTED.
check_eq() {
    local test_name="$1"
    local expected="$2"
    shift 2

    local output status
    output=$("$KTEXT" "$@" 2>/tmp/cond_test_err.$$)
    status=$?
    output=$(printf '%s' "$output" | trim)

    if [ $status -ne 0 ]; then
        echo "${red}FAIL${reset} $test_name — ktext exited $status"
        echo "       stderr: $(head -3 /tmp/cond_test_err.$$)"
        FAIL=$((FAIL + 1))
        return
    fi
    if [ "$output" = "$expected" ]; then
        echo "${green}PASS${reset} $test_name"
        PASS=$((PASS + 1))
    else
        echo "${red}FAIL${reset} $test_name"
        echo "       expected: [$expected]"
        echo "       got:      [$output]"
        FAIL=$((FAIL + 1))
    fi
}

# check_contains TEST_NAME SUBSTRING KTEXT_ARGS...
#   Runs ktext, expects exit status 0, and checks that stdout contains SUBSTRING.
check_contains() {
    local test_name="$1"
    local needle="$2"
    shift 2

    local output status
    output=$("$KTEXT" "$@" 2>&1)
    status=$?

    if [ $status -ne 0 ]; then
        echo "${red}FAIL${reset} $test_name — ktext exited $status"
        echo "       output: $(echo "$output" | head -3)"
        FAIL=$((FAIL + 1))
        return
    fi
    if echo "$output" | tr '\n' ' ' | tr -s ' ' | grep -qF "$needle"; then
        echo "${green}PASS${reset} $test_name"
        PASS=$((PASS + 1))
    else
        echo "${red}FAIL${reset} $test_name — expected to contain [$needle]"
        echo "       output: $(echo "$output" | head -3)"
        FAIL=$((FAIL + 1))
    fi
}

# check_error TEST_NAME PATTERN KTEXT_ARGS...
#   Runs ktext, expects a NONZERO exit status and PATTERN in the message.
check_error() {
    local test_name="$1"
    local pattern="$2"
    shift 2

    local output status
    output=$("$KTEXT" "$@" 2>&1)
    status=$?

    if [ $status -eq 0 ]; then
        echo "${red}FAIL${reset} $test_name — expected an error but ktext succeeded"
        FAIL=$((FAIL + 1))
        return
    fi
    if echo "$output" | tr '\n' ' ' | tr -s ' ' | grep -qF "$pattern"; then
        echo "${green}PASS${reset} $test_name"
        PASS=$((PASS + 1))
    else
        echo "${red}FAIL${reset} $test_name — expected error to contain [$pattern]"
        echo "       output: $(echo "$output" | head -3)"
        FAIL=$((FAIL + 1))
    fi
}

FRAC='@@frac a | b : *a*/*b* @@'

# A file for the @read non-strictness cases (21-21b).
READ_FIXTURE=$(mktemp "${TMPDIR:-/tmp}"/cond_read.XXXXXX)
printf 'READ-FIXTURE\n' > "$READ_FIXTURE"
trap 'rm -f "$READ_FIXTURE"' EXIT

echo "${bold}@cond argument delimitation tests${reset}"
echo "================================="
echo

# --- The reported regression (defined klammer with bars inside a branch) ---

check_eq \
    " 1. inner klammer with bars, true branch" \
    "1/2" \
    -s "$FRAC @cond true | @frac 1 | 2 @ | @frac 2 | 1 @ @" -d

check_eq \
    " 2. inner klammer with bars, false branch" \
    "2/1" \
    -s "$FRAC @cond false | @frac 1 | 2 @ | @frac 2 | 1 @ @" -d

# --- The exact witness file from the bug report ---

check_contains \
    " 3. tst/cond_test.kt @cond_klammer_test true" \
    "1/2" \
    "$K/tst/cond_test.kt" -d -s '@cond_klammer_test true @'

check_contains \
    " 4. tst/cond_test.kt @cond_klammer_test false" \
    "2/1" \
    "$K/tst/cond_test.kt" -d -s '@cond_klammer_test false @'

# --- Plain @cond unaffected by the change ---

check_eq " 5. plain two-bar, true"  "yes" -s '@cond true | yes | no @' -d
check_eq " 6. plain two-bar, false" "no"  -s '@cond false | yes | no @' -d
check_eq " 7. one-bar, true"        "shown" -s '@cond true | shown @' -d
check_eq " 8. one-bar, false (empty)" "" -s '@cond false | shown @' -d

# --- Primitives and nesting inside @cond ---

check_eq " 9. @eval in a branch"      "42"  -s '@cond true | @eval 6*7 @ | no @' -d
check_eq "10. @eval as the predicate" "yes" -s '@cond @eval 1==1 @ | yes | no @' -d
check_eq "11. nested @cond in a branch" "B" -s '@cond true | @cond false | A | B @ | C @' -d

# --- A klammer with its own bars (double-bar / cells) inside a branch ---

check_eq "12. klammer with internal bar in a branch" \
    "x+y" \
    -s '@@two a | b : *a*+*b* @@ @cond true | @two x | y @ | z @' -d

# --- Genuine arity errors must still be rejected ---

check_error "13. three top-level bars is still an error" \
    "one or two bar characters" \
    -s '@cond true | a | b | c @' -d

check_error "14. zero bars is still an error" \
    "one or two bar characters" \
    -s '@cond true @' -d

# --- The predicate relation: TOTAL AND STRICT (Andy, 2026-08-15) ---
#
# Deciding notes/Klammertext_improvements.md §4.1.  There is a defined true
# set, a defined false set, and anything else is an error AT THE @cond.  It was
# partial until then: is_true() recognized three strings and everything else
# took the false branch, so a misspelled variable, a "TRUE", a "yes", or a
# Python traceback all silently selected a branch.  A warning had made that
# visible while the policy was open; it never fired on the SKS, which is the
# evidence that the blast radius is small.

echo
echo "-- the predicate relation --"

for p in true True 1; do
    check_eq "15. \"$p\" is true" "T" -s "@cond $p | T | F @" -d
done
for p in false False 0; do
    check_eq "16. \"$p\" is false" "F" -s "@cond $p | T | F @" -d
done

# Empty stays FALSE, and load-bearing: an optional argument that was not
# written substitutes as empty, which is what carries the "@cond *opt*" idiom.
# The entangled sub-question in §4.1 -- empty means false, or means "not
# supplied"? -- is answered "false" by that use.
check_eq "17. an absent optional argument is false" "F" \
    -s '@@g :opt : @cond *opt* | T | F @ @@ @g@' -d
check_eq "17a. ... and the same argument written true is true" "T" \
    -s '@@g :opt : @cond *opt* | T | F @ @@ @g :opt true @' -d

check_error "18. an unrecognized predicate is an error, not false" \
    "is not a truth value" \
    -s '@cond yes | T | F @' -d
check_error "18a. ... including a near miss of a true value" \
    "is not a truth value" \
    -s '@cond TRUE | T | F @' -d
# A state variable in a klammer BODY works: a body is processed at application
# time, after substitution, so @cond sees the value.
check_eq "19. a state variable in a body reaches the @cond" "T" \
    -s '@@@state Flag :value true @@@ @@g : @cond *Flag* | T | F @ @@ @g@' -d

# A top-level state variable reaches the predicate too, since @cond is resolved
# at APPLICATION time (notes/Klammertext_improvements.md §4.2, decided
# 2026-08-15).  It did not until then: a top-level @cond was resolved when the
# file was READ, which is before state substitution, so it saw the literal
# "*Flag*" and silently took the false branch -- the WRONG answer for a flag
# whose value was true.  The document now behaves like a klammer body: its
# state variables are bound before its conditionals are decided.
check_eq "19a. a top-level state variable reaches the @cond" "T" \
    -s '@@@state Flag :value true @@@ @cond *Flag* | T | F @' -d
check_eq "19b. ... and selects the false branch when it is false" "F" \
    -s '@@@state Flag :value false @@@ @cond *Flag* | T | F @' -d

# --- Non-strictness: nothing in a discarded branch runs ---
#
# doc/cond_evaluation_order.md states this ("with side-effecting @read/@eval,
# wrong ... must not read the missing file").  @read honoured it; @eval did not,
# because the eval pass swept the list before the cond pass did.  Both honour it
# now: mark_cond_content() makes a branch inert BEFORE either pass runs.

check_eq "21. a @read in a discarded branch is not performed" "ok" \
    -s "@cond false | @read $READ_FIXTURE @ | ok @" -d
check_eq "21a. ... and IS performed when the branch is selected" "READ-FIXTURE" \
    -s "@cond true | @read $READ_FIXTURE @ | ok @" -d
# The case the design document names: the file need not even exist.
check_eq "21b. ... so a missing file in a discarded branch is not an error" "ok" \
    -s '@cond false | @read /nonexistent/no-such-file.txt @ | ok @' -d

# An @eval side effect is the observable test: the branch either touched the
# file or it did not.
SIDE=$(mktemp -u "${TMPDIR:-/tmp}"/cond_side.XXXXXX)
"$KTEXT" --klammersets none -s "@cond false | @eval :shell touch $SIDE @ | ok @" -d >/dev/null 2>&1
if [ -f "$SIDE" ]; then
    echo "${red}FAIL${reset} 22. an @eval in a discarded branch ran"; FAIL=$((FAIL+1)); rm -f "$SIDE"
else
    echo "${green}PASS${reset} 22. an @eval in a discarded branch does not run"; PASS=$((PASS+1))
fi
"$KTEXT" --klammersets none -s "@cond true | @eval :shell touch $SIDE @ | ok @" -d >/dev/null 2>&1
if [ -f "$SIDE" ]; then
    echo "${green}PASS${reset} 22a. ... and does run when the branch is selected"; PASS=$((PASS+1)); rm -f "$SIDE"
else
    echo "${red}FAIL${reset} 22a. an @eval in the selected branch did not run"; FAIL=$((FAIL+1))
fi

# The PREDICATE is always evaluated -- a conditional that could not compute its
# own predicate would be useless.  Only the branches are non-strict.
check_eq "23. the predicate is evaluated even though the branches are not" "yes" \
    -s '@cond @eval 1==1 @ | yes | no @' -d
# The recognized sets are named in the message, since the whole point is that
# the writer has to know what they are.
check_error "20. the message names the recognized values" \
    "true, True, 1" \
    -s '@cond yes | T | F @' -d

rm -f /tmp/cond_test_err.$$

echo
echo "================================="
echo "Results: ${green}$PASS passed${reset}, ${red}$FAIL failed${reset}"
[ $FAIL -eq 0 ]